Customer Case Study

Sanford Health is an integrated health system headquartered in the Dakotas and with over 28,000 employees is now the largest rural, not-for-profit health care system in the nation.



Vertical Use Case

  • Using machine learning to provide customized treatments for patients, based on their own circumstances and genetic background, rather than a “one size fits all” sort of treatment

Technical Use Case

  • Data Ingest and ETL
  • Machine Learning

The Challenges

  • Need to analyze massive patient datasets (e.g. 100k+ genomes, medical images, health records) to identify genetic mutations responsible for chronic disease
  • Lack of DevOps and engineering expertise made it difficult to set up and scale the necessary infrastructure to support analytics and ML
  • In the past, they would have to spend months or even years to set up the necessary capabilities to perform machine learning at scale

The Solution

Databricks provides Sanford Health with a unified analytics platform that allows them to process and analyze clinical and genetic data, while at the same time, maintaining the data integrity required for HIPAA compliance.

  • Fully managed cloud platform simplifies data engineering and operations so data scientists and statisticians can focus on the data in AWS S3
  • Automated cluster management allows the team to easily provision and scale clusters on-demand reducing time to insight from days to hours
  • Able to incorporate larger amounts of data into their models to provide better preventative care and precision medicine
  • Interactive workspace allows data scientists to collaborate, share and track data and insights, fostering an environment of transparency and improving clinical validation

Databricks allows us to take clinical research and development and turn it into a clinically validated screen in far less time, which allows us to save us a lot of the money and effort it would generally require to do this on our own on-premises computational platforms.

Lynn Carmichael, Senior Director of Computational Bioinformatics at Sanford Health